GPT-3.5 (Generative Pre-trained Transformer 3.5) is a large language model created by OpenAI. It was pre-trained on both code and code inputs. The code inputs came from GitHub.
architecture
The non-chat variants of the GPT-3.5 models accept a suffix parameter, which can be used to ask the LLM to fill in text between the prompt and suffix. They were trained using OpenAI's Efficient Training of Language Models to Fill in the Middle} paper.
release
text-davinci-002, a 3.5 variant trained with FeedME, was available on the OpenAI API since at least early 2022.
code-davinci-002, the base model, was available to some users since early 2022 but was removed from the API for most users in March 2023.
text-davinci-003, a variant trained with reinforcement learning from human feedback, was released on the API on November 28, 2022.
chatGPT-3.5 was released on November 30, 2022.
variants
base model
code-davinci-002 (cd2) is the base model of GPT-3.5.
text-davinci-002
text-davinci-003
chatGPT
chatGPT-3.5 (cGPT-3.5, gpt-3.5-turbo on the API) is the first chatGPT model, released by OpenAI on November 30, 2022. It is based on GPT-3.5 and tuned using reinforcement learning from human feedback.